NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DA6BSYMG4H4NDCFAYRA7KK
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3.8s
Cost:
$0.000218
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
20.19%
Matches word count
(details)
81.36%
Dialogue to Total Word Ratio
(details)
50.7759%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
"Okay, Bill, the plan is simple. We slip through the back window while the clown's doing balloon animals," Molly whispered, adjusting her ski mask. "Simple? Molly, the clown has a chainsaw-sized balloon pump. I saw him at the gate." "Which is why we bring the cake. Nobody suspects a guy carrying cake." "Nobody suspects a guy carrying cake because nobody wants to be near that cake. It's got a fork in it." "Fine. Then you distract the kids with your card tricks." "My card tricks are terrible. Last time, a six-year-old made me cry." "Bill, you cried because he beat you at Go Fish." "He cheated. He had a lucky hat." "Focus. Presents are stacked by the piano. Blue wrapping means bikes, shiny paper means video games, and that lumpy one is definitely a puppy." "We can't steal a puppy, Molly." "It's a stuffed puppy. Relax." "Still feels wrong." "Then grab the bigger boxes. Nobody counts the bigger boxes." "You're the brains, I'm just the guy with the sack." "And the sack says 'Santa' on it, so keep it low-key."
created_at
"2026-10-08T08:31:04.52Z"
10/8/2026, 8:31:04 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
809
moderation_latency
(null)
generation_time
3733
tokens_prompt
75
tokens_completion
265
native_tokens_prompt
95
native_tokens_completion
416
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"end_turn"
service_tier
"default"
usage
0.0002175
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448264-l9HBtG1J1zr2sLpfyXOj"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448264-MSwrzKR48A3PvqlTGLHB"
upstream_id
"msg_011CfpTWye4Wcm2wsXiDj5Tb"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpTWye4Wcm2wsXiDj5Tb"
is_byok
false
latency
809
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0002175
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Claude Platform on AWS"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
20.19%
Matches word count
n/a
neededClean
false
words
180
81.36%
Dialogue to Total Word Ratio
Ratio: 96.74%, Deviation: 6.74%
neededClean
false
wordsTotal
184
wordsDialogue
178
50.7759%